TY - CHAP AU - Ridha, A.A. AU - Almaameri, Ihab AU - Blázovics, László AU - Abbas, H.M. ED - IEEE, , TI - Human Activity Recognition by BiLSTM Recurrent Neural Networks and Support Vector Machine T2 - 6th Iraqi International Conference on Engineering Technology and its Applications, IICETA 2023 PB - IEEE CY - Piscataway (NJ) SN - 9798350303339 PY - 2023 SP - 459 EP - 465 PG - 7 DO - 10.1109/IICETA57613.2023.10351372 UR - https://m2.mtmt.hu/api/publication/34533661 ID - 34533661 N1 - Education in Najaf, Ministry of Education, Najaf, Iraq Budapest University of Technology and Economics, Department of Automation and Applied Informatics, Budapest, Hungary The Islamic University, Najaf, Iraq Conference code: 195754 Export Date: 26 January 2024 AB - In the last years of this decade, the recognition of human activity has become important to a wide range of researchers in pattern recognition and human-computer interaction as a result of its wide range of real-world applications, such as gesture recognition, biometric user identification, surveillance by authorities, behavior analysis and health monitoring of the elderly. Human Activity Recognition (HAR) has become a significant topic in mobile and ubiquitous computing as a result of the widespread use of wearable sensor devices and the Internet of Things (loT). Deep Learning (DL) is one of the most commonly used problem-solving techniques in the HAR system. Nevertheless, there are major challenges in applying HAR to problems in recognizing various human activities. In this paper, presented and showed the activities of implementing a new combination of DL methods for multi-class user activity identification to HAR. Using DL methods can be extracting discriminative features automatically from raw sensor data. Specifically, in this work, we proposed a hybrid architecture that features a combination of Bidirectional Long Short-Term Memory (BILSTM) networks and support vector Machines (SVM) for the HAR task. The UCI HAR dataset is used to test the model, it consists of accelerometer and gyroscope data obtained from smartphones. The dataset is split into 30 % for testing and 70% for training. The results for the (BILSTM-SVM) model, showed that the highest accuracy for all users was 98.74 %, higher than all previous models using the same dataset. © 2023 IEEE. LA - English DB - MTMT ER - TY - CHAP AU - Almaameri, Ihab AU - Blázovics, László ED - IEEE, , TI - An Overview of Drones Communication, Application and Challenge in 5G Network T2 - 6th Iraqi International Conference on Engineering Technology and its Applications, IICETA 2023 PB - IEEE CY - Piscataway (NJ) SN - 9798350303339 PY - 2023 SP - 67 EP - 73 PG - 7 DO - 10.1109/IICETA57613.2023.10351413 UR - https://m2.mtmt.hu/api/publication/34451727 ID - 34451727 N1 - Export Date: 18 March 2024 LA - English DB - MTMT ER - TY - CHAP AU - Hideg, Attila AU - Blázovics, László AU - Lukovszki, Tamás AU - Forstner, Bertalan ED - Klempous, Ryszard ED - Nikodem, Jan ED - Baranyi, Péter Zoltán TI - RobotCore—A General Multi-robot Simulation Framework T2 - Accentuated Innovations in Cognitive Info-Communication PB - Springer Netherlands CY - Cham SN - 9783031109560 T3 - Topics in Intelligent Engineering and Informatics, ISSN 2193-9411 ; 16. PY - 2023 SP - 239 EP - 258 PG - 20 DO - 10.1007/978-3-031-10956-0_12 UR - https://m2.mtmt.hu/api/publication/33123947 ID - 33123947 AB - In the last decade, research targeting multi-robot systems has increased due to the advantageous properties of those systems. They might be cost-efficient, scalable, and fault-tolerant; however, the development of these systems is more complicated. These features increase the desire to create algorithms that can be hard to test and validate. Therefore, these algorithms have to be formalized; then, they can be implemented on simulators, which brings the demand for a simulation framework that can perform, execute, and validate the algorithms for multi-robot systems, even at large scales, which is still flexible enough to allow the integration of new problem sets and algorithms. With this in mind, the authors present a general robot simulation framework, called the RobotCore framework. LA - English DB - MTMT ER - TY - JOUR AU - Hideg, Attila AU - Blázovics, László AU - Lukovszki, Tamás AU - Forstner, Bertalan TI - Uniform Dispersal of Cheap Flying Robots in the Presence of Obstacles JF - ACTA POLYTECHNICA HUNGARICA J2 - ACTA POLYTECH HUNG VL - 18 PY - 2021 IS - 1 SP - 13 EP - 28 PG - 16 SN - 1785-8860 DO - 10.12700/APH.18.1.2021.1.2 UR - https://m2.mtmt.hu/api/publication/31840392 ID - 31840392 N1 - Department of Automation and Applied Informatics, Budapest University of Technology and Economics, Magyar tudósok krt. 2, Budapest, H-1117, Hungary Faculty of Informatics, Eötvös Loránd University, Pázmány P. sétány 1/c, Budapest, H-1117, Hungary Cited By :1 Export Date: 25 October 2022 LA - English DB - MTMT ER - TY - CHAP AU - Hideg, Attila AU - Blázovics, László AU - Forstner, Bertalan TI - Uniform Dispersal of Cheap Flying Robots T2 - 10th IEEE International Conference on Cognitive Infocommunications, (CogInfoCom 2019) PB - IEEE CY - Piscataway (NJ) SN - 9781728147925 T3 - International Conference on Cognitive Infocommunications, ISSN 2375-1312 PY - 2019 SP - 227 EP - 232 PG - 6 DO - 10.1109/CogInfoCom47531.2019.9089977 UR - https://m2.mtmt.hu/api/publication/31640712 ID - 31640712 N1 - Conference code: 159695 Export Date: 25 October 2022 LA - English DB - MTMT ER - TY - CHAP AU - Hideg, Attila AU - Blázovics, László AU - Forstner, Bertalan TI - Multi-Robot Simulation Framework T2 - 9th IEEE International Conference on Cognitive Infocommunications (CogInfoCom) PB - IEEE CY - Piscataway (NJ) SN - 1538670941 T3 - International Conference on Cognitive Infocommunications, ISSN 2375-1312 PY - 2018 SP - 159 EP - 163 PG - 5 DO - 10.1109/CogInfoCom.2018.8639911 UR - https://m2.mtmt.hu/api/publication/30905039 ID - 30905039 N1 - Export Date: 28 May 2020 AB - In this paper a general robot simulation framework is created, called RobotCore. The simulation is mostly used to provide experimental results to theoretical analysis for multi-robot systems. However, in certain cases, theoretical analysis can be difficult and it might be more adequate to check the effectiveness of different methods in those experiments before analyzing them. The framework provides a three-dimensional visualizer, to depict the movements and actions of the robots. Moreover, this visualizer can be used to upgrade or debug the algorithms while they are running. Additionally, the framework includes a component for extensive testing on vast number of test scenarios. LA - English DB - MTMT ER - TY - CHAP AU - Hideg, Attila AU - Blázovics, László AU - Csorba, Kristóf AU - Gótzy, Márton ED - Baranyi, Péter Zoltán ED - Sallai, Gyula TI - Data Collection for Widely Distributed Mass of Sensors T2 - 7th IEEE Conference on Cognitive Infocommunications - COGINFOCOM 2016 PB - IEEE Hungary Section CY - Budapest SN - 9781509026432 PY - 2016 SP - 193 EP - 198 PG - 6 DO - 10.1109/CogInfoCom.2016.7804548 UR - https://m2.mtmt.hu/api/publication/3154097 ID - 3154097 N1 - Cited By :4 Export Date: 28 May 2020 LA - English DB - MTMT ER - TY - CHAP AU - Hideg, Attila AU - Blázovics, László AU - Forstner, Bertalan ED - Baranyi, Péter Zoltán ED - Sallai, Gyula TI - Uniform Dispersal of Oblivious Mobile Robots T2 - 7th IEEE Conference on Cognitive Infocommunications - COGINFOCOM 2016 PB - IEEE Hungary Section CY - Budapest SN - 9781509026432 PY - 2016 SP - 323 EP - 326 PG - 4 DO - 10.1109/CogInfoCom.2016.7804569 UR - https://m2.mtmt.hu/api/publication/3154086 ID - 3154086 LA - English DB - MTMT ER - TY - CHAP AU - Hetényi, D AU - Gótzy, M AU - Blázovics, László ED - Szakál, Anikó TI - Sensor fusion with enhanced Kalman Filter for altitude control of quadrotors T2 - 2016 IEEE 11TH INTERNATIONAL SYMPOSIUM ON APPLIED COMPUTATIONAL INTELLIGENCE AND INFORMATICS (SACI) PB - IEEE CY - Budapest SN - 9781509023813 PY - 2016 SP - 413 EP - 418 PG - 6 DO - 10.1109/SACI.2016.7507412 UR - https://m2.mtmt.hu/api/publication/3127143 ID - 3127143 LA - English DB - MTMT ER - TY - CHAP AU - Gotzy, M AU - Hetenyi, D AU - Blázovics, László ED - Ciganek, J ED - Kozak, S ED - Kozakova, A TI - Aerial Surveillance System with Cognitive Swarm Drones T2 - 2016 Cybernetics & Informatics (K&I) PB - IEEE CY - New York, New York SN - 9781509018321 PY - 2016 SP - 1 EP - 6 PG - 6 DO - 10.1109/CYBERI.2016.7438593 UR - https://m2.mtmt.hu/api/publication/3121337 ID - 3121337 N1 - Cited By :2 Export Date: 28 May 2020 AB - Due to the increasing computational capacity of embedded systems, the design of aerial surveillance drones became affordable. However individual robots are less efficient than those who are forming a collective. These systems mostly use decentralised algorithms and communication networks. We present a distributed, communication aided solution for a problem in which a group of autonomous mobile robots patrol over a given area and intercept the detected targets. The robots are oblivious, they use local sensing, and they can share information within their neighbourhood. We adopt the Multi-Orbit-Surrounding (MOS) based Aerial Surveillance concept into a square grid graph based environment, and we will prove that the concept can detect and surround an intruder in finite time. LA - English DB - MTMT ER -